Debug & triage
5,138 rows, by stacks then stars
1,113 of these skill files have been read, by 1,020 distinct authors, and what they tell an agent counted. What Debug & triage authors agree on, and what they forbid
qa-veritas/skillpack/skills/generate_triage_plan Skill
0★ repoProduce an ordered investigation plan from a failure classification and the available evidence sources, with explicit stop conditions so the investigation ends when the next step would not change the conclusion. Use at the start of any non-trivial failure.
qa-veritas/skillpack/skills/identify_root_cause Skill
0★ repoFrom all collected findings, pick the single most-likely root cause with a confidence level, the supporting evidence, and the cheapest test that would falsify it. Use as the synthesis step at the end of a triage.
qa-veritas/skillpack/skills/summarize_logs Skill
0★ repoCompress a log slice into a timeline, clustered errors, and a one-paragraph summary. Never read a multi-GB log end to end. Use to make a large log tractable.
Andiedie/skills/skills/ai-native-development/and-triage Skill
no license0★ repoDecide whether recorded work should close, wait for information, or be packed.
selamy-labs/agent-skills/skills/email-triage Skill
0★ repoUse when building or operating an agent email triage loop that turns recent inbox messages into prioritized, source-linked actions without duplicating project-specific rules across agents.
Myra-Agents/skills/skills/debug Skill
0★ repoInteractive runtime-evidence debugger for ANY language (frontend, backend, CLI, worker, mobile, shell). USE THIS (instead of adding a print/console.log and asking the user to eyeball it) when about to: "add a log and ask user to check", "open DevTools and tell me what you see", "reproduce the bug and share the output", "check the console/terminal output". Triggers: "debug this", "fix this bug", "why isn't this working", "investigate this issue", "trace the problem", "value is null/undefined", "request returns wrong data", "handler never runs", "UI not updating", "panic/exception thrown". Runs a localhost log server, instruments code, asks YOU to reproduce, reads logs directly (no copy-paste), then interactively confirms with you whether the bug is fixed before cleaning up.
HaloForgeAI/aegis-agent-plugins/plugins/aegis/skills/aegis-operator Skill
0★ repoUse Aegis from Codex as an AI assistant. Trigger when the user asks to inspect, capture, triage, assign, dispatch, report, clean up, or diagnose Aegis work through the configured aegis MCP server. Do not trigger for simple one-off chat unless Aegis state should be read or changed.
HaloForgeAI/aegis-agent-plugins/skills/aegis Skill
0★ repoOperate Aegis, an AI assistant for personal owner work and small-team execution. Use when the user wants to capture durable work, triage or clean a board, assign real or virtual members, dispatch Aegis Coder/local workers, review status, manage memory/context candidates, or diagnose Gateway/local worker health through Aegis MCP tools. Do not use for ordinary one-off chat unless the user explicitly wants Aegis state updated.
shuymn/skills/skills/triage-review Skill
no license0★ repoProcesses AI reviewer feedback and applies only verified fixes. Works in two modes: (1) fetches comments from a PR URL or current branch, (2) processes feedback pasted directly into the conversation. Trigger when the user wants to bulk-process or apply AI review suggestions — from a GitHub PR or pasted text. Do NOT trigger for single questions about what a bot said, or general code review discussion.
percymcn/agent-cookbook/skills/software-development/debugging-hermes-tui-commands Skill
0★ repoDebug Hermes TUI slash commands: Python, gateway, Ink UI.
The same file is in 1 other repository
percymcn/agent-cookbook/skills/software-development/software-delivery-workflow Skill
0★ repoSoftware delivery workflow umbrella: planning, spikes/prototypes, test-driven development, systematic debugging, debugger use, and pre-commit code review/verification. Use for class-level engineering process guidance before or during code changes.
Aws sdk error handling canonical
esaldgut/ai-native-engineering-workspace/global-skills/aws-go/aws-sdk-error-handling-canonical Skill
0★ repoHandle AWS SDK Go v2 errors the canonical way — errors.As against typed/modeled errors and the smithy.APIError interface — and NEVER strings.Contains(err.Error(), "...") to silence or branch on an SDK error. String-matching error text breaks silently across SDK upgrades and, worse, masks a deeper bug: if a "silenced" error fires on every normal invocation, the API is being called in a context AWS does not support (e.g. AdminLinkProviderForUser in PreSignUp). Use when writing or reviewing any error-handling branch around an AWS SDK Go v2 call, especially one that treats an error as "idempotent / already exists / edge case OK."
llupin4/mindframes/skills/investigative-reasoning Skill
no license0★ repoApply Abductive Reasoning and Socratic Method for diagnostic, investigative, and root-cause work. Use when the user needs to figure out why something happened, how to get from one state to another, debug a complex system, uncover hidden assumptions, or trace a causal chain. Trigger on phrases like "why did", "root cause", "what happened", "how did we get here", "figure out", "debug", "investigate", "diagnose", "migrate from X to Y", "what changed", "what went wrong", or "help me understand why". Also use for incident triage, post-mortems, and migration planning.
rossinsilico/loop-anything/.agents/skills/loop-triage Skill
0★ repoSelect one bounded task for an agent loop from visible state, real repo evidence, permission boundaries, and a named proof command.
rossinsilico/loop-anything/templates/loop-pack/skills/loop-triage Skill
0★ repoSelect one bounded task for an agent loop from visible state, real repo evidence, permission boundaries, and a named proof command.
tdyzzsp47/claude-skills/skills/debugging Skill
0★ repoバグの再現・原因特定・修正・再発防止までを科学的手順でカバーするスキル。「動かない・おかしい・落ちる」など原因不明の不具合調査が必要なときに使う。
mtkhawaja/java-skills/skills/java-observability Skill
0★ repoUse when adding, reviewing, or retrofitting logging, metrics, tracing, or diagnostics in Java — including "improve the logging/observability of this code" requests. Covers the logging facade with parameterized structured messages, the full level palette (DEBUG/INFO/WARN/ERROR) across a unit of work, correlation IDs / MDC, never logging secrets/PII, preserving stack traces, and Micrometer / OpenTelemetry. Catches string-concatenated logs, System.out, sensitive-data logging, and missing correlation/telemetry.
krkrkrr/skills/skills/frontend/frontend-review-triage Skill
no license0★ repoUse when starting a frontend review engagement or when the user asks for an initial assessment ("triage", "day 0", "what's the state of this repo"). Reads package.json, README, gh issues, and produces a scorecard covering lockfiles, TypeScript strictness, testing, CI, and known issues. Runs `scripts/audit-triage.sh`.
vincendiary/agents/skills/triage Skill
no license0★ repoTriage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
The same file is in 14 other repositories
agent-packs/registry/skills/debugging-and-error-recovery Skill
no license0★ repoReproduce, localize, reduce, fix, and guard against failures. Use when tests fail, builds break, or behavior is unexpected.
bobmmao/agent-workflow-skills/skills/governance/memory-triage Skill
0★ repoALWAYS USE THIS SKILL. Persistent long-term memory protocol powered by mem0. After EVERY response, evaluate the conversation for durable facts worth storing via memory_store. Handles identity, preferences, decisions, configurations, rules, projects, and relationships. Use memory_store (NOT workspace files) for all user facts. Read this skill at the start of every session.
stevancris/sre-ai-agent/skills/import-rca Skill
0★ repoTransform any RCA or postmortem document into a reusable knowledge-base pattern. Accepts any company format — Google SRE, Atlassian, PagerDuty, Elastic, plain text, Confluence export, or free-form notes. Extracts and distills the incident into a structured failure pattern that the agent can search in future incidents. Trigger keywords: import rca, convert postmortem, add to knowledge base, import incident, we have an old RCA, transform postmortem, bulk import RCA, add past incident, import from confluence, convert our incident report.
stevancris/sre-ai-agent/skills/observability Skill
0★ repoDesign, review, and improve observability for services: metrics, logs, and distributed traces. Use when instrumenting a new service, investigating gaps in visibility, reviewing dashboards, building alerting, or diagnosing why an incident was hard to detect. Trigger keywords: observability, metrics, logs, tracing, traces, dashboard, alerting, instrumentation, OpenTelemetry, Prometheus, Datadog, Grafana, structured logging, spans, golden signals, USE method, RED method, four golden signals, visibility, monitoring gap, hard to debug, missing metrics, no alerts.
stevancris/sre-ai-agent/skills/rca-summary Skill
0★ repoGenerate a concise, shareable RCA (Root Cause Analysis) summary from raw incident data, postmortem notes, or a completed root-cause-analysis skill session. Use when you need to communicate findings quickly to stakeholders, produce a Slack or email digest of an RCA, create a one-pager for management, or add a brief RCA entry to a knowledge base. Distinct from the full postmortem or deep root-cause-analysis skill — this produces a tight, readable summary optimized for sharing. Trigger keywords: RCA summary, summarize RCA, RCA one-pager, share the RCA, brief RCA, quick summary of what happened, executive RCA, RCA for management, send the findings, incident summary, what happened summary, TL;DR of the incident, incident digest, share postmortem findings, RCA writeup, brief postmortem.
stevancris/sre-ai-agent/skills/root-cause-analysis Skill
0★ repoSystematically identify root causes of incidents, bugs, and reliability failures. Use after an incident, when debugging a persistent reliability problem, or when a postmortem needs structured analysis. Covers five-whys, fishbone diagrams, timeline correlation, and contributing factor categorization. Trigger keywords: root cause, RCA, why did this happen, five whys, contributing factors, investigation, debugging production, what caused, correlation, timeline analysis, why is this happening, keep happening, recurring incident, same problem again.
nichtlegacy/kometa-skill/skills/kometa-debug-review Skill
0★ repoUse whenever the user asks why Kometa YAML fails, asks for review, has indentation problems, has the wrong top-level key, mixed up file types, missing connectors, or wants a broken config repaired. Use this skill aggressively for any Kometa troubleshooting or review request.
goharabbas321/zeoel/skills/agent-introspection-debugging Skill
no license0★ repoStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
The same file is in 5 other repositories
goharabbas321/zeoel/skills/error-handling Skill
no license0★ repoPatterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages.
The same file is in 2 other repositories
goharabbas321/zeoel/skills/systematic-debugging Skill
no license0★ repoUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
The same file is in 30 other repositories
vemodalen-x/VEMO_SKILLS/skills/orchestration/designing-diagnostic-prompts Skill
0★ repoDesign structured diagnostic or tutoring prompts and agent workflows that interview the user, locate constraints, configure style/depth, produce a plan, and loop through assessment and feedback. Use when asked to create or improve a Human 3.0-style self-discovery prompt, a Mr. Ranedeer-style tutor prompt, a coaching/custom GPT prompt, an onboarding interview, a diagnostic agent, a personalized learning flow, or any multi-turn prompt that must ask questions before advising.
Fix sentry exception paper cut
tomquirk/papercut-skills/fix-sentry-exception-paper-cut Skill
0★ repoAnalyse recent production Sentry errors with sentry-cli, then fix and publish exactly one isolated unhandled error paper cut. Use when Codex should inspect Sentry issues or events for a target web app, choose a small current exception, handle it with a clear user-facing failure path or structured internal logging, run verification, and open a new draft PR without hiding unexpected bugs.
mikulgohil/claude-skills/skills/fundamentals/debugging Skill
0★ repoSystematic debugging methodology — reproduce, isolate, hypothesize, verify — plus language-specific debuggers and common-scenario playbooks (leaks, races, deadlocks, crashes). Use when tracking down a bug of unknown cause.
KhurrumMahmood/senior-vibe-engineer/.claude/skills/diagnose Skill
no license0★ repoBuild a trustworthy debugging loop for hard bugs, regressions, and intermittent failures before changing code. Use when a symptom is unclear, a bug has not been reproduced, a performance regression needs measurement, or a fix would otherwise be based on guesswork.
KhurrumMahmood/senior-vibe-engineer/.claude/skills/triage-debt Skill
no license0★ repoCross-cutting aggregator that scores accumulated debt across the maintenance loop's outputs (find-* report stacks, spec drift, decision drift, hard-size-overflow specs, recurring same-target hits) and produces a ranked queue at `reports/triage-debt/scan-<TS>/queue.md`. Each entry names the recommended next skill to invoke (refactor-subsystem / fix-workflow / extract-* / decide). Top-5 highlighted. Pure read — never edits production code, never runs find-*; reads the cached evidence those skills already produced.
markstent/muster/skills/triage Skill
0★ repo(Muster) Sorts your tasks, judges how risky each one is, and marks the safe ones ready to build on their own. Reads your code; only writes issue labels and comments, never code itself. Run after /spec, before /build.
hillzeealex/skills/engineering/diagnosing-bugs Skill
no license0★ repoDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
The same file is in 17 other repositories
hillzeealex/skills/engineering/triage Skill
no license0★ repoMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
The same file is in 13 other repositories
0xgetz/xi-agent-skills/mcp-skills/datadog-mcp Skill
no license0★ repoUse the Datadog MCP integration to query metrics, logs, and monitors. Activate when the user wants to query metrics, logs, and monitors via Datadog, including discovering the right tool, building parameters, and handling results.
0xgetz/xi-agent-skills/mcp-skills/sentry-mcp Skill
no license0★ repoUse the Sentry MCP integration to read and triage error monitoring issues. Activate when the user wants to read and triage error monitoring issues via Sentry, including discovering the right tool, building parameters, and handling results.
ctoth/golang-skills-plugin/plugins/golang/skills/go-error-handling Skill
0★ repoAgent skill plugins for Go code quality and performance work.
ctoth/golang-skills-plugin/plugins/golang/skills/go-slog-logging Skill
0★ repoAgent skill plugins for Go code quality and performance work.
ctoth/golang-skills-plugin/plugins/performant-golang/skills/go-perf-production-incidents Skill
0★ repoGuides diagnosing a LIVE Go performance incident under on-call pressure — OOMKill / RSS climb, GC death-spiral / CPU pegged in GC, p99 latency cliff, goroutine leak / pile-up, CPU saturation — with the capture-evidence-before-restart discipline, safe prod pprof / flight-recorder / heap-profile runbooks, and GOMEMLIMIT triage. Auto-invokes on "my service is OOMing", "production latency spiked", "pod keeps getting OOMKilled", "diagnose this incident", "goroutines climbing in prod", "CPU pegged in GC". Routes GC knobs to go-perf-gc-tuning, tail latency to go-perf-tail-latency, the tracer/flight recorder to go-perf-execution-tracer.
Yco-0314/strata/skills/l4-review/debugging Skill
0★ repoUse when the user reports a bug, a test failure, a crash, unexpected behavior, or a performance regression, or says "debug"/"diagnose"/"it's broken"/"why is this failing". Builds a tight red-capable feedback loop before any hypothesis, finds the root cause, and fixes the shared function once. Auto-fires on any failure.
yuelenghan/orbit/skills/github-issue Skill
0★ repoUse when the user needs GitHub issue and milestone-backed tracker operations through the packaged launcher and local CLI runtime.
chenwei791129/es-log-cli/.agents/skills/spectra-debug Skill
0★ repoSystematically debug a problem using a four-phase workflow
cipradu/Agent-Workbench/skills/error-handling-design Skill
0★ repoUse when designing, changing, or reviewing application error handling, runtime validation failures, error taxonomies, result envelopes, exception mapping, sanitized messages, retryability, fallback/degraded-mode behavior, error aggregation, cleanup, correlation IDs, logging, or redaction behavior.
sharklandy/claude-code-starter-kit/skills/process/bug-triage-runbook-template Skill
0★ repoDiagnose and categorize incoming user feedback or bug reports. Trigger whenever processing a message from <TODO: nom du canal ou de la source des retours, ex. #feedback>.
sharklandy/claude-code-starter-kit/skills/process/systematic-debugging Skill
0★ repoGeneric runbook to diagnose any bug or unexpected behavior. Trigger whenever asked to fix a bug, investigate an error, or explain why something isn't working — before proposing a fix.
udsy19/.claude/skills/debugging-and-error-recovery Skill
no license0★ repoGuides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
The same file is in 75 other repositories
ch040602/skill-vaccine/tests/fixtures/benchmark_expansion/prior_replace_triage Skill
no license0★ repoCovers paraphrased agent-context priority manipulation in project workflows.
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Business & Ops/org-health-diagnostic Skill
0★ repoCross-functional organizational health check combining signals from all C-suite roles. Scores 8 dimensions on a traffic-light scale with drill-down recommendations. Use when assessing overall company health, preparing for board reviews, identifying at-risk functions, or when user mentions org health, health check, or health dashboard.
The same file is in 2 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Creative/debugging-toolkit-smart-debug Skill
0★ repoUse when working with debugging toolkit smart debug
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Creative/debugging-toolkit Skill
0★ repoUse when working with debugging toolkit smart debug (Alias for debugging-toolkit-smart-debug)
The same file is in 5 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Creative/error-diagnostics-smart-debug Skill
0★ repoUse when working with error diagnostics smart debug
The same file is in 7 other repositories
Claude in chrome troubleshooting
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/claude-in-chrome-troubleshooting Skill
0★ repoDiagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.
The same file is in 5 other repositories
Error debugging multi agent review
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/error-debugging-multi-agent-review Skill
0★ repoUse when working with error debugging multi agent review
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Design/linux-troubleshooting Skill
0★ repoLinux system troubleshooting workflow for diagnosing and resolving system issues, performance problems, and service failures.
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/debug-buttercup Skill
0★ repoAll pods run in namespace crs. Use when pods in the crs namespace are in CrashLoopBackOff, OOMKilled, or restarting, multiple services restart simultaneously (cascade failure), or redis is unresponsive or showing AOF warnings.
The same file is in 5 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/debugger Skill
0★ repo'Debugging specialist for errors, test failures, and unexpected
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/debugging-strategies Skill
0★ repoTransform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and methodical approaches.
The same file is in 6 other repositories